[GitHub] [spark] dongjoon-hyun commented on a change in pull request #27836: [SPARK-31009][SQL] Support json_object_keys function

[GitBox <gi...@apache.org>]

dongjoon-hyun commented on a change in pull request #27836: [SPARK-31009][SQL] Support json_object_keys function
URL: https://github.com/apache/spark/pull/27836#discussion_r400636486
 
 

 ##########
 File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/jsonExpressions.scala
 ##########
 @@ -796,3 +797,64 @@ case class SchemaOfJson(
 
   override def prettyName: String = "schema_of_json"
 }
+
+/**
+ * A function which returns all the keys of outer JSON object.
+ */
+@ExpressionDescription(
+  usage = "_FUNC_(json_object) - returns all the keys of outer JSON object.",
+  arguments = """
+    Arguments:
+      * json_object - A JSON object. If it is an invalid string, the function returns null.
+          If it is a JSON array or null, a runtime exception will be thrown.
+  """,
+  examples = """
+    Examples:
+      > Select _FUNC_('{}');
+        []
+      > Select _FUNC_('{"key": "value"}');
+        ["key"]
+      > Select _FUNC_('{"f1":"abc","f2":{"f3":"a", "f4":"b"}}');
+        ["f1","f2"]
+  """,
+  since = "3.1.0")
+case class JsonObjectKeys(child: Expression) extends UnaryExpression with CodegenFallback {
+  override def dataType: DataType = ArrayType(StringType)
+  override def nullable: Boolean = true
+  override def prettyName: String = "json_object_keys"
+
+  override def eval(input: InternalRow): Any = {
+    try {
+      val json = child.eval(input).asInstanceOf[UTF8String]
+      Utils.tryWithResource(CreateJacksonParser.utf8String(SharedFactory.jsonFactory, json)) {
+        parser => getJsonKeys(parser, input)
+      }
+    } catch {
+      case _: JsonProcessingException => null
+    }
 
 Review comment:
   Apparently, the current implementation seems to have the same limitations: `NullPointerException` and `ClassCastException`. Please add more unit test cases with `null` and `Integer` input.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org